Fault analysis method and system adapted to hydro-photovoltaic-storage grid source system, medium and device

Abstract

The present invention relates to the technical field of power system fault analysis. Disclosed are a fault analysis method and system adapted to a hydro-photovoltaic-storage grid source system, a medium, and a device. The system of the present invention comprises a multi-source data acquisition and preprocessing module, a fault feature extraction and classification module, a fault location module, a fault impact assessment module, and a dynamic update and adaptation module. The method of the present invention comprises the following steps: multi-source data acquisition and preprocessing, fault feature extraction and classification, fault location and impact assessment, and dynamic update and adaptive adjustment. Provided in the present invention is the fault analysis method adapted to a hydro-photovoltaic-storage grid source system, which is capable of comprehensively and accurately analyzing various types of faults in complex power systems; comprehensively considering characteristics of various components of a system can achieve rapid and accurate fault type identification, fault location and fault impact range assessment, thereby providing strong support for instant and effective fault handling and ensuring stable and reliable operation of power systems.

Description

Analysis methods, systems, media, and equipment for adapting to faults in hydro-solar-storage-grid power generation systems. Technical Field

[0001] This invention relates to the field of power system fault analysis technology, and in particular to analysis methods, systems, media and equipment adapted to fault analysis of hydro-solar-storage-grid-source systems. Background Technology

[0002] With the continued growth in global demand for clean energy, integrated power systems combining hydropower, photovoltaic power generation, energy storage, and traditional grid power have emerged as a new type of power system. This system has demonstrated significant advantages in improving energy efficiency and promoting the integration of renewable energy. However, due to the complexity and diversity of its components and the significant differences in characteristics between them, fault analysis has become extremely challenging. Technical issues

[0003] Traditional power system fault analysis methods primarily target power systems with relatively simple or homogeneous structures. In contrast, each component of a hydro-solar-storage-grid-source power system possesses its own unique characteristics.

[0004] For example, hydropower is affected by intermittent changes in water flow, photovoltaic power depends on sunlight intensity and temperature, the charging and discharging states of energy storage systems are constantly changing, and there are also complex interactions between different power sources. These factors together make the fault characteristics of hydro-photovoltaic-storage-grid-source power systems complex and variable.

[0005] Existing power system fault analysis methods often fail to fully consider all the aforementioned factors when dealing with hydro-solar-storage-grid power systems. Therefore, these methods suffer from insufficient accuracy and low efficiency in fault type identification, fault location, and fault impact assessment.

[0006] For example, when photovoltaic power generation experiences sudden power fluctuations and triggers a fault due to cloud cover, traditional methods may be unable to accurately determine whether the fault originates from the photovoltaic equipment itself or from a system anomaly caused by changes in the external environment. This ambiguity in judgment may delay fault handling, thereby adversely affecting the stable operation of the power system.

[0007] Therefore, in order to solve the above problems, it is necessary to design analysis methods and systems that are adapted to the faults of the hydro-solar-storage-grid-source system. Technical solutions

[0008] The technical problem this invention aims to solve is to overcome the shortcomings of existing technologies by designing an analysis method and system adapted to faults in hydro-solar-storage-grid-source power systems. This includes a multi-source data acquisition and preprocessing module responsible for collecting data from various key nodes of the hydro-solar-storage-grid-source power system and preprocessing the collected data; a fault feature extraction and classification module that designs feature extraction algorithms to extract fault features and performs classification training on the extracted fault features; a fault location module for accurately calculating fault locations; a fault impact assessment module for evaluating the scope and degree of fault impact on various parts of the power system; and a module for real-time monitoring of the operating parameters and structural changes of the fault analysis system, automatically updating the parameters and algorithms of the fault analysis system, and utilizing online learning technology to allow the model to continuously learn, optimize, dynamically update, and adapt. Through data acquisition, preprocessing, feature extraction, fault classification, fault location, and fault impact assessment, this invention can comprehensively and accurately analyze various faults in this complex power system. By comprehensively considering the characteristics of each component of the system, it achieves rapid and accurate fault type identification, fault location, and fault impact range assessment, providing strong support for timely and effective fault handling and ensuring the stable and reliable operation of the power system.

[0009] The solution adopted by this invention to solve its technical problem is as follows:

[0010] An analysis system adapted to faults in a hydro-solar-storage-grid power generation system.

[0011] Its features are,

[0012] Include:

[0013] The multi-source data acquisition and preprocessing module is responsible for acquiring data from various key nodes of the hydro-solar-storage-grid-source power system and preprocessing the acquired data.

[0014] The fault feature extraction and classification module is used to design feature extraction algorithms to extract fault features and to perform classification training on the extracted fault features.

[0015] The fault location module is used to accurately calculate the fault location.

[0016] The fault impact assessment module is used to assess the scope and extent of the impact of a fault on various parts of the power system.

[0017] The dynamic update and adaptive module is used to monitor the operating parameters and structural changes of the fault analysis system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to enable the model to continuously learn and optimize.

[0018] In a preferred embodiment of the present invention, the features to be extracted by the fault feature extraction and classification module include:

[0019] Harmonic characteristics of electrical quantities and abrupt changes in active and reactive power of generators extracted in response to generator faults in hydropower plants.

[0020] Correlation characteristics between light intensity and output power and abnormal temperature change characteristics of photovoltaic panels were extracted for photovoltaic power plant faults.

[0021] The slope changes and abnormal fluctuations in the state of charge of the battery are extracted in response to energy storage system faults.

[0022] In a preferred embodiment of the present invention, the fault impact assessment module uses a power flow calculation algorithm to assess the impact of a fault on the power system.

[0023] An analytical method for adapting to faults in a hydro-solar-storage-grid power generation system.

[0024] Its features are,

[0025] Includes the following steps:

[0026] S1. Data Acquisition and Preprocessing

[0027] Data is collected from key nodes of hydropower plants, photovoltaic power plants, energy storage systems, and power grids. The collected raw data is preprocessed by noise removal, missing value imputation, format conversion, and time alignment.

[0028] S2. Fault Feature Extraction and Classification

[0029] To address the fault characteristics of different components in a hydropower-solar-storage-grid power system, a feature extraction algorithm was designed to extract fault features from hydropower plant generators, photovoltaic power stations, energy storage systems, and the power grid. A machine learning classification algorithm was then used to classify the extracted fault features and determine the fault type of the collected data.

[0030] S3. Fault location and impact assessment

[0031] Based on the fault type determination results, combined with the power system topology and electrical parameters, a location algorithm is used to accurately calculate the fault location. Furthermore, a power flow calculation model is established to assess the scope and extent of the fault's impact on various parts of the power system.

[0032] S4, Dynamic Updates and Adaptive Adjustments

[0033] The system monitors the operating conditions and structural changes of the power system in real time, automatically updates the parameters and algorithms of the fault analysis system, and uses online learning technology to feed new fault cases back into the fault analysis system for optimization.

[0034] In a preferred embodiment of the present invention, the feature extraction algorithm in step S2 includes:

[0035] A harmonic analysis algorithm designed for faults in hydropower plant generators utilizes Fourier transform to perform spectral analysis of electrical quantities, extracting the amplitude and phase characteristics of specific harmonics. Simultaneously, it monitors abrupt changes in active and reactive power, sets power change thresholds, and extracts the rate and amplitude of power changes and related characteristics when power changes exceed these thresholds.

[0036] A mathematical model of illuminance and output power is established for photovoltaic power plant design. Fault characteristics are extracted by real-time monitoring of the deviation between illuminance and output power. Simultaneously, real-time analysis of photovoltaic panel temperature data is performed; when the temperature rises abnormally or fluctuates excessively, the gradient and duration of temperature changes, along with related characteristics, are extracted.

[0037] The slope changes of the battery charge-discharge curves for energy storage system design are analyzed. By calculating the changes in battery voltage and current at adjacent time points, the slope characteristics of the charge-discharge curves are obtained. Abnormal fluctuations in the state of charge are monitored. When the state of charge changes significantly in a short period of time, the amplitude and frequency of the change in state of charge are extracted.

[0038] In a preferred embodiment of the present invention, the positioning algorithm in step S3 includes:

[0039] For the double-ended traveling wave method used to locate faults in transmission lines, traveling wave measuring devices are installed at both ends of the transmission line to accurately record the arrival time of the fault traveling wave at both ends. The time data from both ends is transmitted to the fault location calculation center via a communication system. Based on the line wave velocity and time difference formulas, the distance from the fault point to both ends is calculated, thereby locating the fault.

[0040] For the impedance method of internal equipment faults in hydropower plants, photovoltaic power stations, and energy storage systems, the specific location of the fault point inside the equipment is determined by measuring the change in electrical impedance of the faulty equipment, combined with the electrical connection diagram and fault characteristics of the equipment.

[0041] In a preferred embodiment of the present invention, noise removal in step S1 is performed using the Kalman filtering algorithm; missing value filling is performed using linear interpolation or by combining historical data statistical patterns.

[0042] In a preferred embodiment of the present invention, the machine learning classification algorithms used in step S2 include support vector machines and random forests.

[0043] A computer-readable storage medium,

[0044] It stores a computer program, which, when executed by a processor, implements the aforementioned analysis method for adapting to faults in a hydro-solar-storage-grid-source system.

[0045] A computer device,

[0046] include:

[0047] Processor and memory;

[0048] The memory is used to store computer programs;

[0049] The processor is used to execute the computer program stored in the memory, so that the computer device performs the above-described analysis method for adapting to faults in the hydro-solar-storage-grid-source system. Beneficial effects

[0050] 1. High-precision fault analysis: The system of this invention comprehensively collects multi-source data and deeply mines the fault characteristics of each part. Combined with advanced machine learning classification algorithms, it significantly improves the accuracy of fault type judgment and improves the accuracy of fault analysis compared with traditional methods.

[0051] In terms of fault location, the method of this invention employs a variety of advanced location algorithms, providing a strong guarantee for rapid fault repair.

[0052] 2. High efficiency and rapid response: The entire fault analysis process has been optimized and designed. From the occurrence of a fault to the completion of fault type identification, location and impact assessment, the time taken is shorter than that of traditional methods, which improves the timeliness of fault handling and reduces power outage time and economic losses caused by faults.

[0053] 3. Strong Adaptability and Scalability: The dynamic update and adaptive adjustment modules of this invention enable the method to adapt well to the constantly changing characteristics of hydro-solar-storage-grid-source power systems. It maintains excellent fault analysis capabilities regardless of system structure adjustments or changes in operating conditions. Furthermore, the method is easily expandable, readily integrating new monitoring equipment and analysis algorithms to meet the needs of future power system development.

[0054] 4. Improve system stability: Accurate fault analysis helps to take timely and effective fault handling measures, reduce the impact of faults on the power system, maintain the stability of the system's voltage and frequency, and improve the operational reliability and stability of the entire hydro-solar-storage-grid-source power system. Attached Figure Description

[0055] Figure 1 is a schematic diagram of the structure of the analysis system for adapting to faults in the hydro-solar-storage-grid power generation system proposed in this invention;

[0056] Figure 2 is a schematic diagram of the analysis method for adapting to faults in the hydro-solar-storage-grid power generation system proposed in this invention. Embodiments of the present invention

[0057] The specific embodiments of the present invention are described below with reference to the accompanying drawings and examples:

[0058] It should be noted that the structures, colors, proportions, sizes, etc. shown in the accompanying drawings are only used to complement the content disclosed in the specification, so that those skilled in the art can understand and read them, and are not intended to limit the conditions under which the present invention can be implemented. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0059] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "setting," "connection," "fixing," "screw connection," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal connection of two components or the interaction between two components. Unless otherwise explicitly limited, those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0060] The accompanying drawings in this specification are only used to complement the content disclosed in the specification, so that those skilled in the art can understand and read them. They are not intended to limit the conditions under which the present invention can be implemented. Any modifications to the structure, changes in proportions, or adjustments to size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0061] As shown in Figure 1, this invention proposes an analysis system for faults in a hydro-solar-storage-grid power generation system, which includes a multi-source data acquisition and preprocessing module, a fault feature extraction and classification module, a fault location module, a fault impact assessment module, and a dynamic update and adaptive module.

[0062] Multi-source data acquisition and preprocessing module:

[0063] Responsible for collecting data from various key nodes of the hydro-solar-storage-grid-source power system and preprocessing the collected data;

[0064] Fault Feature Extraction and Classification Module:

[0065] This study designs a feature extraction algorithm to extract fault features from different components of a hydro-solar-storage-grid-source power system, and then performs classification training on the extracted fault features.

[0066] Fault location module:

[0067] It is used to accurately calculate the fault location based on the fault type judgment result, and to set different positioning algorithms for different parts;

[0068] Fault Impact Assessment Module:

[0069] Used to assess the scope and extent of the impact of a fault on various parts of the power system;

[0070] Dynamic update and adaptive module:

[0071] It is used to monitor the operating parameters and structural changes of the fault analysis system in real time, automatically update the parameters and algorithms of the fault analysis system, and continuously feed new fault cases and corresponding analysis results into the classification model using online learning technology, so that the classification model can continuously learn and optimize, thereby improving its ability to analyze various complex faults.

[0072] Selection of data acquisition equipment and its installation location in the hydro-solar-storage-grid power generation system in the multi-source data acquisition and preprocessing module:

[0073] 1. In hydropower plants, high-precision turbine sensors are selected and installed in key parts of the turbine, such as the inlet pipe, volute, and main shaft, to collect parameters such as flow rate, water pressure, and rotational speed.

[0074] On the generator side, a power quality monitoring device is installed to collect electrical quantities such as voltage, current, and power.

[0075] 2. In a photovoltaic power station, each row of photovoltaic panels is equipped with a temperature sensor and a light intensity sensor, and the data is transmitted to a centralized processing unit through a data acquisition device;

[0076] Install power monitoring equipment at the output of the photovoltaic inverter.

[0077] 3. For energy storage systems, voltage and current sensors are installed on each battery module of the battery pack to monitor the battery status in real time.

[0078] 4. In the power grid, install smart meters, phasor measurement units (PMUs), and other equipment at key nodes of substations and transmission lines to collect electrical parameters of the power grid.

[0079] The fault feature extraction and classification module collects a large amount of historical fault data and normal operation data from hydropower plants, photovoltaic power plants, energy storage systems, and power grids, and divides them into training and test sets according to a certain ratio. During feature classification training, a machine learning classification algorithm is selected. Based on the dimension and distribution of the fault features, an appropriate kernel function (such as the radial basis function kernel) is chosen to train the model on the training set data. The model parameters in the fault feature extraction and classification module are adjusted to achieve optimal classification performance.

[0080] In actual operation, the fault features extracted in real time are input into the trained classification model to quickly determine the fault type. At the same time, the classification model is regularly updated and trained using new fault data to improve its adaptability and accuracy.

[0081] The dynamic update and adaptive module is included in the system monitoring program set up in the power system operation management center. It is used to monitor changes in the operating parameters of hydropower plants, photovoltaic power plants, energy storage systems and power grids in real time, such as the addition and removal of equipment, and the adjustment of the range of power generation.

[0082] When changes in system structure or operating parameters are detected, the parameter update program within the dynamic update and adaptive module is automatically triggered. For electrical parameters in the fault analysis model, such as the resistance and reactance of transmission lines and the turns ratio of transformers, updates are made according to the actual equipment changes. For threshold parameters in the fault feature extraction algorithm, such as power change thresholds and temperature anomaly thresholds, recalculations and adjustments are made according to the new operating conditions.

[0083] The dynamic update and adaptive module also utilizes online learning technology to record the results of each fault analysis and the corresponding fault data, forming new learning samples. These new samples are periodically input into the machine learning classification model, and an incremental learning algorithm is used to update and train the model, enabling it to learn new fault modes and features. Simultaneously, the fault location and impact assessment algorithms are optimized. Based on feedback from actual fault handling processes, the algorithm parameters and computational logic are adjusted to continuously improve the overall performance of the fault analysis method.

[0084] Figure 2 shows an analysis method for faults in a hydro-solar-storage-grid power generation system.

[0085] Includes the following steps:

[0086] S1. Data Acquisition and Preprocessing

[0087] Collect relevant data from key nodes of hydropower plants, photovoltaic power plants, energy storage systems, and power grids, and perform preprocessing operations such as noise removal, missing value imputation, format conversion, and time alignment on the collected raw data;

[0088] The data collected from key nodes includes:

[0089] 1. Operating parameters of the hydropower plant's turbines, such as flow rate, water pressure, and speed;

[0090] 2. Electrical quantities of the generator, such as voltage, current, and power;

[0091] 3. Photovoltaic panel temperature, light intensity, and output power of the photovoltaic power station;

[0092] 4. Battery voltage, current, and state of charge of the energy storage system;

[0093] 5. Information on voltage, current, phase, etc. at different locations on the power grid.

[0094] In the background data processing server, a data preprocessing program was written, employing the Kalman filter algorithm for noise removal. State equations and observation equations were established based on the dynamic characteristics of electrical quantities, and the real-time acquired data was filtered.

[0095] Temporary data loss due to sensor malfunction requires missing value imputation, which can be performed using linear interpolation or by combining historical data statistical patterns.

[0096] Specifically, based on the time series characteristics of the data, if the data gap is short, linear interpolation is used to calculate the interpolation using data from adjacent time points; if the gap is long, the data is filled in by combining the statistical patterns of historical data.

[0097] For format conversion and time alignment of different types of data, a unified data format standard should be established, such as adopting the relevant standard format of the International Electrotechnical Commission; data collected by different devices should be aligned according to a unified time base through timestamp marking and synchronization algorithms.

[0098] S2. Fault Feature Extraction and Classification

[0099] To address the fault characteristics of different components in a hydropower-solar-storage-grid power system, a fault feature extraction algorithm is designed to extract fault features from hydropower plant generators, photovoltaic power stations, energy storage systems, and the power grid. A machine learning classification algorithm is then used to classify the extracted fault features and determine the fault type of the collected data.

[0100] The features extracted when extracting fault features include:

[0101] 1. For generator failures in hydropower plants, extract the harmonic characteristics of electrical quantities and the abrupt change characteristics of active and reactive power.

[0102] 2. For photovoltaic power plants, extract the correlation characteristics between light intensity and output power, and the abnormal temperature change characteristics of photovoltaic panels;

[0103] 3. For energy storage systems, extract features such as the slope changes of the battery charge and discharge curves and abnormal fluctuations in the state of charge.

[0104] The designed feature extraction algorithm includes:

[0105] 1. A harmonic analysis algorithm designed for faults in hydropower plant generators utilizes Fourier transform to perform spectral analysis of electrical quantities, extracting the amplitude and phase characteristics of specific harmonics. Simultaneously, it monitors abrupt changes in active and reactive power, sets a power change threshold, and extracts the rate and amplitude of power change and related characteristics when the power change exceeds the threshold.

[0106] 2. A mathematical model of light intensity and output power is established for the design of photovoltaic power plants. This model is used to monitor deviations between light intensity and output power in real time and extract fault characteristics. Simultaneously, real-time analysis of photovoltaic panel temperature data is performed. When the temperature rises abnormally or fluctuates excessively, the gradient and duration of temperature changes, along with related characteristics, are extracted.

[0107] 3. For the design of energy storage systems, analyze the slope changes of battery charge and discharge curves. By calculating the changes in battery voltage and current at adjacent times, obtain the slope characteristics of the charge and discharge curves. Monitor abnormal fluctuations in the state of charge. When the state of charge changes significantly in a short period of time, extract the characteristics such as the amplitude and frequency of the change in the state of charge.

[0108] After feature extraction, classification algorithms from machine learning, such as Support Vector Machine (SVM) and Random Forest, are used to train the extracted fault features for classification. A training set is constructed using a large amount of historical fault data and normal operation data, allowing the classification model to learn the feature patterns corresponding to different fault types, thereby enabling rapid and accurate identification of fault types from real-time collected data.

[0109] S3. Fault location and impact assessment

[0110] Based on the fault type determination results, combined with the power system topology and electrical parameters, a location algorithm is used to accurately calculate the fault location, and a power flow calculation model is established to assess the scope and degree of the fault's impact on various parts of the power system.

[0111] After determining the fault type, an appropriate location algorithm is selected based on the power system part where the fault is located. Location algorithms include improved impedance methods, traveling wave methods, and other location algorithms.

[0112] For transmission line faults, if the double-ended traveling wave method is used, traveling wave measuring devices are installed at both ends of the transmission line to accurately record the arrival time of the fault traveling wave at both ends. The time data from both ends is transmitted to the fault location calculation center through a communication system, and the distance from the fault point to both ends is calculated based on the line wave velocity and time difference formula.

[0113] For equipment failures within hydropower plants, photovoltaic power stations, and energy storage systems, an impedance matching-based location method is used, combining the equipment's electrical connection diagram and fault characteristics, to pinpoint the specific location of the fault within the equipment by measuring the electrical impedance changes of the faulty equipment.

[0114] By establishing a power flow calculation model for the power system, the redistribution of power flow after a fault occurs is simulated, and the impact on the output of each power source, the voltage of load nodes, and the power transmission of transmission lines is analyzed. Simultaneously, the regulating role of the energy storage system is considered, and its contribution to maintaining system stability under fault conditions is evaluated.

[0115] Energy storage systems, as an important regulation tool, play a crucial role in system failures. Through rapid charging and discharging, energy storage systems can balance power imbalances caused by faults, helping to maintain system frequency and voltage stability. Simultaneously, energy storage systems can provide necessary power support during the fault recovery phase, accelerating the system's recovery process.

[0116] The power flow calculation model employs a series of mature power flow calculation algorithms, such as the Newton-Raphson method and the fast decomposition method. These algorithms are based on the fundamental theory of power systems and solve for the power flow distribution of the system through mathematical iteration, enabling efficient handling of complex calculation problems in large-scale power systems. The specific calculations are input with the power system topology, electrical parameters, and the initial states of each power source and load. After a fault occurs, the corresponding parameters in the model are adjusted according to the fault type and location; for example, the impedance of the faulty line is set to infinity to simulate the impact of the fault on the system's power flow.

[0117] Power flow calculations are used to obtain the changes in power output, load node voltage, and transmission line power transmission after a fault, assessing the scope and extent of the fault's impact on the power system. Simultaneously, the charging and discharging regulation role of the energy storage system during a fault is fully considered. Based on the real-time status and control strategy of the energy storage system, the power injection of the energy storage system in the power flow calculation model is adjusted in real time, analyzing the contribution of the energy storage system to maintaining system stability.

[0118] S4, Dynamic Updates and Adaptive Adjustments

[0119] The system monitors the operating conditions and structural changes of the power system in real time, automatically updates the parameters and algorithms of the fault analysis system, and uses online learning technology to feed new fault cases back into the fault analysis system for optimization.

[0120] As power system operating conditions change and new equipment is added or old equipment is upgraded, system characteristics will alter. By monitoring the operating parameters and structural changes of the fault analysis system in real time, the parameters and algorithms of the fault analysis model are automatically updated. This ensures the accuracy and effectiveness of the fault analysis system for integrated hydro-solar-storage-grid-source power systems. It contributes to improving the stability and reliability of power systems, providing strong support for the widespread application of clean energy.

[0121] Furthermore, it is necessary to continuously improve and optimize the algorithms and models, implementation steps, and safeguards of the fault analysis system to adapt to the ever-changing operating conditions and equipment characteristics of the power system. For example, when a photovoltaic power station adds a new photovoltaic panel array, the fault feature extraction algorithm and classification model for the photovoltaic section should be adjusted in a timely manner to adapt to the new power generation characteristics.

[0122] At the same time, by utilizing online learning technology, new fault cases and corresponding analysis results are continuously fed back into the fault analysis system, allowing the fault analysis system to continuously learn and optimize, thereby improving its ability to analyze various complex faults.

[0123] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned analysis method for adapting to faults in a hydro-solar-storage-grid-source system.

[0124] Those skilled in the art will understand that:

[0125] All or part of the steps in the above-described method embodiments can be implemented using computer program-related hardware. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps included in the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0126] Computer-readable and writable storage media may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, flash memory, USB flash drive, portable hard drive, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer.

[0127] A computer device includes: a processor and a memory; the memory is used to store computer programs; the processor is used to execute the computer programs stored in the memory, so that the computer device performs the above-described analysis method for adapting to faults in a hydro-solar-storage-grid power generation system.

[0128] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0129] Many other changes and modifications can be made without departing from the concept and scope of this invention. It should be understood that this invention is not limited to the specific embodiments, and the scope of this invention is defined by the appended claims.

Claims

1. An analysis system adapted to faults in a hydro-solar-storage-grid power generation system. Its features are, Include: The multi-source data acquisition and preprocessing module is responsible for acquiring data from various key nodes of the hydro-solar-storage-grid-source power system and preprocessing the acquired data. The fault feature extraction and classification module is used to design feature extraction algorithms to extract fault features and to perform classification training on the extracted fault features. The fault location module is used to accurately calculate the fault location. The fault impact assessment module is used to assess the scope and extent of the impact of a fault on various parts of the power system. The dynamic update and adaptive module is used to monitor the operating parameters and structural changes of the fault analysis system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to enable the model to continuously learn and optimize.

2. The analysis system for adapting to faults in a hydro-solar-storage-grid power generation system as described in claim 1. Its features are, The fault feature extraction and classification module needs to extract the following features when extracting fault features: Harmonic characteristics of electrical quantities and abrupt changes in active and reactive power of generators extracted in response to generator faults in hydropower plants. Correlation characteristics between light intensity and output power and abnormal temperature change characteristics of photovoltaic panels were extracted for photovoltaic power plant faults. The slope changes and abnormal fluctuations in the state of charge of the battery are extracted in response to energy storage system faults.

3. The analysis system for adapting to faults in a hydro-solar-storage-grid power generation system as described in claim 2. Its features are, The fault impact assessment module uses power flow calculation algorithms to assess the impact of faults on the power system.

4. An analytical method for faults in a hydro-solar-storage-grid power generation system. The system employs the fault analysis method described in claim 3 for adapting to hydro-solar-storage-grid power generation system. Its features are, Includes the following steps: S1. Data Acquisition and Preprocessing Data is collected from key nodes of hydropower plants, photovoltaic power plants, energy storage systems, and power grids. The collected raw data is preprocessed by noise removal, missing value imputation, format conversion, and time alignment. S2. Fault Feature Extraction and Classification To address the fault characteristics of different components in a hydropower-solar-storage-grid power system, a fault feature extraction algorithm is designed to extract fault features from hydropower plant generators, photovoltaic power stations, energy storage systems, and the power grid. A machine learning classification algorithm is then used to classify the extracted fault features and determine the fault type of the collected data. S3. Fault location and impact assessment Based on the fault type judgment results, combined with the power system topology and electrical parameters, a location algorithm is used to accurately calculate the fault location, and a power flow calculation model is established to evaluate the scope and degree of the fault's impact on various parts of the power system. S4, Dynamic Updates and Adaptive Adjustments The system monitors the operating conditions and structural changes of the power system in real time, automatically updates the parameters and algorithms of the fault analysis system, and uses online learning technology to feed new fault cases back into the fault analysis system for optimization.

5. The analysis method for adapting to faults in a hydro-solar-storage-grid power generation system as described in claim 4. Its features are, The feature extraction algorithm in step S2 includes: A harmonic analysis algorithm designed for faults in hydropower plant generators utilizes Fourier transform to perform spectral analysis of electrical quantities, extracting the amplitude and phase characteristics of specific harmonics. Simultaneously, it monitors abrupt changes in active and reactive power, sets power change thresholds, and extracts the rate and amplitude of power changes and related characteristics when power changes exceed these thresholds. A mathematical model of light intensity and output power is established for photovoltaic power plant design. Fault characteristics are extracted by real-time monitoring of the deviation between the two. Simultaneously, real-time analysis of photovoltaic panel temperature data is performed. When the temperature rises abnormally or fluctuates excessively, the gradient and duration of temperature changes, along with related characteristics, are extracted. The slope changes of the battery charge-discharge curves for energy storage system design are analyzed. By calculating the changes in battery voltage and current at adjacent time points, the slope characteristics of the charge-discharge curves are obtained. Monitor abnormal fluctuations in the state of charge (SOC). When the SOC changes significantly in a short period of time, extract features such as the amplitude and frequency of the change.

6. The analysis method for adapting to faults in a hydro-solar-storage-grid power generation system as described in claim 5, Its features are, The localization algorithm in step S3 includes: For the double-ended traveling wave method for transmission line faults, traveling wave measuring devices are installed at both ends of the transmission line to accurately record the arrival time of the fault traveling wave at both ends. The time data from both ends is transmitted to the fault location calculation center via a communication system. Based on the line wave velocity and time difference formula, the distance from the fault point to both ends is calculated. For the impedance method of internal equipment faults in hydropower plants, photovoltaic power stations, and energy storage systems, the specific location of the fault point inside the equipment is determined by measuring the change in electrical impedance of the faulty equipment, combined with the electrical connection diagram and fault characteristics of the equipment.

7. The analysis method for adapting to faults in a hydro-solar-storage-grid power generation system as described in claim 6. Its features are, In step S1, noise removal is performed using the Kalman filter algorithm; missing value filling is performed using linear interpolation or by combining historical data statistical patterns.

8. The analysis method for adapting to faults in a hydro-solar-storage-grid power generation system as described in claim 7. Its features are, The machine learning classification algorithms used in step S2 include support vector machines and random forests.

9. A computer-readable storage medium having a computer program stored thereon, Its features are, When the computer program is executed by the processor, it implements the analysis method for adapting to faults in the hydro-solar-storage-grid power generation system as described in claim 8.

10. A computer device, Its features are, include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory, so that the computer device performs the analysis method for adapting to faults in the hydro-solar-storage-grid power generation system as described in claim 8.

Images